© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7469
    Prev
    Next
    INDEX
    Explanations

    college or university references

    np_acts-logits-general · gemini-2.5-flash-lite

    widely available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سمت
    0.40
    jong
    0.38
    esz
    0.38
     তত্ত্ব
    0.38
     দুটো
    0.38
     //{
    0.38
    leton
    0.37
    纹
    0.37
    inj
    0.36
    tek
    0.36
    POSITIVE LOGITS
    Shortcut
    0.35
     SCRE
    0.35
    設定
    0.35
    зво
    0.35
     परिश
    0.35
    ट्रोल
    0.35
     দিতেন
    0.34
     resale
    0.34
     wink
    0.34
    非常有
    0.34
    Activations Density 0.002%

    No Known Activations